I’ve rolled a small program to enforce consistency, lint rules, and human-authored files for Claude Memory.
It’s insanely powerful when doing by a human 100%. It’s conversely harmful when an agent manages it. There’s several papers about how LLM-managed memory is unequivocally terrible.
Indeed. I find it quite bizarre that just about the only thing the LLM appears incapable of doing is writing appropriate instructions for an LLM - whether it be memories, sub agent prompts, planning documents.
It’s insanely powerful when doing by a human 100%. It’s conversely harmful when an agent manages it. There’s several papers about how LLM-managed memory is unequivocally terrible.